In [1]:
import numpy as np
import pandas as pd
In [2]:
print('Numpy Version:',np.__version__)
print('Pandas Version:',pd.__version__)
Q1. Read the '.csv' file into a data frame and display the first 5 rows.¶
In [3]:
df = pd.read_csv('Forbes_Billionaire.csv')
df.head()
Out[3]:
Q2. Name the top 8 industries with maximum count of billionaires¶
In [4]:
pd.DataFrame(df.groupby('Industries')['Name'].nunique()).sort_values(by='Name',ascending=False).head(8)
Out[4]:
In [5]:
df_top8 = pd.DataFrame(df.groupby('Industries')['Name'].nunique()).reset_index().sort_values(by='Name',ascending=False).head(8)
df_top8
Out[5]:
In [6]:
df_top8.iloc[0:8,0:1]
Out[6]:
Q3. State the headcount of billionaires from these top 8 industries¶
In [7]:
df_top8
Out[7]:
Q4. Compare the mean of net worth of billionaires from these top 8 industries.¶
In [8]:
## Creating a new data frame for storing the values of only the top 8 industries with the maximum billionaires
new_df_top8 = pd.DataFrame(columns=df.columns)
new_df_top8
Out[8]:
In [9]:
## Running a loop to get 8 industries with the most number of billionaries
for i in df_top8['Industries']:
a = df[df['Industries']==i] #subsetting the original data frame with these industries
new_df_top8 = new_df_top8.append(a) # appending the subset into the new data frame created in the last steo
In [10]:
new_df_top8
Out[10]:
In [11]:
new_df_top8['Industries'].unique()
Out[11]:
In [12]:
for i in new_df_top8['Industries'].unique():
print('The average net worth of the billionaires of the industry',i,'is',new_df_top8[new_df_top8['Industries']==i]['Net Worth'].mean(),'billions.')
In [13]:
print('The mean net worth of the billionaires from these industries is:',round(new_df_top8['Net Worth'].mean(),3),'billions.')
Q5. Compare the mean age of billionaires from these top 8 industries.¶
In [14]:
for i in new_df_top8['Industries'].unique():
print('The average age of the billionaires of the industry',i,'is',new_df_top8[new_df_top8['Industries']==i]['Age'].mean(),'years.')
In [15]:
print('The mean age of the billionaires from these industries is:',round(new_df_top8['Age'].mean(),2),'years.')
Q6. Name the Richest billionaire in the Automotive sector¶
In [16]:
df['Industries'].unique()
Out[16]:
In [17]:
df[df['Industries']=='Automotive'].sort_values(by='Net Worth',ascending=False).head(1)
Out[17]:
In [18]:
print('The richest billionaires in the Automotive sector is',df[df['Industries']=='Automotive'].sort_values(by='Net Worth',ascending=False).head(1).values[0][1],'with a net worth of',df[df['Industries']=='Automotive'].sort_values(by='Net Worth',ascending=False).head(1).values[0][3],'billions.')
Q7. Name top 5 countries with maximum number of billionaires.¶
In [19]:
df_top5 = pd.DataFrame(df.groupby('Country')['Name'].nunique()).reset_index().sort_values(by='Name',ascending=False).head(5)
df_top5
Out[19]:
In [20]:
df_top5.iloc[0:5,0:1]
Out[20]:
Q8. Which amongst these top 5 countries have the lowest mean age of billionaires ?¶
In [21]:
mean_age_df = pd.DataFrame(columns=['Country','Mean Age'])
mean_age_df
Out[21]:
In [22]:
for i in df_top5['Country']:
mean = df[df['Country']==i]['Age'].mean()
print('The mean age of',i,'is',mean,'years.')
mean_age_df = mean_age_df.append({'Country':i,'Mean Age':mean},ignore_index=True)
In [23]:
mean_age_df.sort_values(by='Mean Age',ascending=True).head(1)
Out[23]:
In [24]:
print('The country which has the lowest mean age amongst the top 5 countries with the maximum number of billionaires is',mean_age_df.sort_values(by='Mean Age',ascending=True).head(1).values[0][0],'with an average age of',round(mean_age_df.sort_values(by='Mean Age',ascending=True).head(1).values[0][1],2),'years.')
Q9. Name the richest Chinese billionaire and his net worth¶
In [25]:
print('The richest Chinese billionaire is',df[df['Country']=='China'].sort_values(by='Net Worth',ascending=False).head(1).values[0][1],'with a Net Worth of',df[df['Country']=='China'].sort_values(by='Net Worth',ascending=False).head(1).values[0][2],'billions.')
Q10. Name top 5 Industries with maximum number of Indian billionaires.¶
In [26]:
pd.DataFrame(df[df['Country']=='India'].groupby('Industries')['Name'].nunique()).reset_index().sort_values(by='Name',ascending=False).head(5)
Out[26]:
In [27]:
print('The top 5 industries with maximum number of Indian billionaires are the following:')
pd.DataFrame(df[df['Country']=='India'].groupby('Industries')['Name'].nunique()).reset_index().sort_values(by='Name',ascending=False).head(5).iloc[0:5,0:1]
Out[27]:
Q11. Name all the Indian billionaires in global top 100 list.¶
In [28]:
top_100 = df.sort_values(by='Net Worth',ascending=False).head(100)
top_100
Out[28]:
In [29]:
top_100[top_100['Country']=='India']['Name'].values
Out[29]:
Q12. Name all the billionaires in India who are younger than 50 years. Also state their mean net worth¶
In [30]:
Indian_billionaires = df[df['Country']=='India']
Indian_billionaires
Out[30]:
In [31]:
print('The names of the Indian Billionaires under the age of 50 are:')
Indian_billionaires[Indian_billionaires['Age']<50]['Name'].values
Out[31]:
In [32]:
print('The average Net Worth of Indian Billionaires below the age of 50 is')
round(Indian_billionaires[Indian_billionaires['Age']<50]['Net Worth'].mean(),3)
Out[32]:
Q13. Name the Indian billionaires from real estate sector who are richer than 'DONALD TRUMP'.¶
In [33]:
df[df['Name']=='DONALD TRUMP']
Out[33]:
In [34]:
Indian_billionaires_realestate = Indian_billionaires[Indian_billionaires['Industries']=='Real Estate']
Indian_billionaires_realestate
Out[34]:
In [35]:
Indian_billionaires_realestate[Indian_billionaires_realestate['Net Worth']>df[df['Name']=='DONALD TRUMP'].values[0][3]]
Out[35]:
In [36]:
print('The Indian billionaires from the Real Estate Industry who are richer than Donald Trump are',Indian_billionaires_realestate[Indian_billionaires_realestate['Net Worth']>df[df['Name']=='DONALD TRUMP'].values[0][3]].iloc[0:2,1:2].values[0][0],'and',Indian_billionaires_realestate[Indian_billionaires_realestate['Net Worth']>df[df['Name']=='DONALD TRUMP'].values[0][3]].iloc[0:2,1:2].values[1][0])
Q14. What is the total cumulative net worth of all the billionaires?¶
In [37]:
df['Net Worth'].sum()
Out[37]: